activity
20242026
collaborators

10 papers

cs.AI2026

Workflow-Localized Mechanism Learning: Attribution-Guided Repair and Knowledge Reuse for Structured Agent Skills

Zibin Lin, Shengli Zhang, Taotao Wang +3

Agent Skills package reusable procedural knowledge as external artifacts for frozen language-model agents, yet existing optimizers do not jointly resolve where a failure occurs in…

cs.AI2026

When Should Agent Trust Be Conditional? Characterizing and Attacking Skill-Conditional Reputation in Agent Swarms

Yihan Xia, Taotao Wang

Open platforms increasingly route tasks among heterogeneous LLM agents--differing in base model, scaffold, and tool stack--whose competence varies sharply by skill: an agent excell…

cs.AI2026

ResearchLoop: An Evidence-Gated Control Plane for AI-Assisted Research

Yihan Xia, Taotao Wang

AI-assisted research compresses ideation, implementation, evaluation, and manuscript writing into a single interactive loop. This compression is useful, but it also creates a publi…

cs.AI2026

Agentic Trading: When LLM Agents Meet Financial Markets

Yihan Xia, Panpan You, Taotao Wang +4

A growing body of work explores how Large Language Models (LLMs) can be embedded in trading systems as agents that perceive market information, retrieve context, reason about decis…

q-fin.CP2026

AlphaLogics: A Market Logic-Driven Multi-Agent System for Scalable and Interpretable Alpha Factor Generation

Zhangyuhua Weng, Shengli Zhang, Taotao Wang +1

Factor investing is ultimately grounded in market logic - the latent mechanism behind observed alpha factors that explains why they should persist across assets and regimes. Howeve…

cs.SD2026

TimberAgent: Gram-Guided Retrieval for Executable Music Effect Control

Shihao He, Yihan Xia, Fang Liu +2

Digital audio workstations expose rich effect chains, yet a semantic gap remains between perceptual user intent and low-level signal-processing parameters. We study retrieval-groun…